microsoft/TRELLIS.2
2 083 points
Intel · Flux
Flux Intel
Ce dont le monde de l'IA parle en ce moment, tiré directement des sources — du plus récent au plus ancien.
2 306 éléments collectés · Page 39 sur 39
Saravutw/WAN2.2_I2V_LIGHTNING_4-8step_custom
272 pointsFrom DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates
Understanding How DeepSeek's Flagship Open-Weight Models Evolved
par Sebastian Raschka, PhDmrfakename/Z-Image-Turbo
3 803 pointsblack-forest-labs/FLUX.2-dev
1 112 pointsfacebook/sam3
3 077 pointsBeyond Standard LLMs
Linear Attention Hybrids, Text Diffusion, Code World Models, and Small Recursive Transformers
par Sebastian Raschka, PhDr3gm/wan2-2-fp8da-aoti-preview
3 046 pointsUnderstanding the 4 Main Approaches to LLM Evaluation (From Scratch)
Multiple-Choice Benchmarks, Verifiers, Leaderboards, and LLM Judges with Code Examples
par Sebastian Raschka, PhDopenbmb/VoxCPM-Demo
755 pointsUnderstanding and Implementing Qwen3 From Scratch
A Detailed Look at One of the Leading Open-Source LLMs
par Sebastian Raschka, PhDFrom GPT-2 to gpt-oss: Analyzing the Architectural Advances
And How They Stack Up Against Qwen3
par Sebastian Raschka, PhDzerogpu-aoti/wan2-2-fp8da-aoti-faster
3 468 pointsThe Big LLM Architecture Comparison
From DeepSeek-V3 to Kimi K2: A Look At Modern LLM Architecture Design
par Sebastian Raschka, PhDmalcolmrey/browser
433 pointsLLM Research Papers: The 2025 List (January to June)
A topic-organized collection of 200+ LLM research papers from 2025
par Sebastian Raschka, PhDpyannote/speaker-diarization-community-1
1 607 pointsblack-forest-labs/FLUX.1-dev
14 570 pointsnanotron/ultrascale-playbook
4 031 pointsDontPlanToEnd/UGI-Leaderboard
2 038 pointsfacebook/mms-300m
455 pointsopenai/clip-vit-base-patch32
1 349 pointssentence-transformers/all-MiniLM-L6-v2
5 825 pointsdistilbert/distilbert-base-uncased
1 292 pointsopenai-community/gpt2
3 942 pointsgoogle-bert/bert-base-uncased
3 130 points